R Notebook

Libraries I may use called

library(tidyverse)
# install for visualizations 
library(ggplot2)
# install to combine date and time
library(lubridate)
# for melting a df
library(reshape)

Reading in the first dataset, perceived health status.

perceived_health_status <- read_csv("../data/perceived_health_status.csv")

Inspecting the data.

perceived_health_status

Filtering.

perceived_health_status_stripped <- perceived_health_status %>% 
  filter(TIME_PERIOD == 2022) %>% 
  filter(REF_AREA == "AUT") %>% 
  filter(Sex == "Total") %>% 
  filter(Age == "15 years or over")  

perceived_health_status_stripped

NA

Explore the time periods the data covers

phs_once <- perceived_health_status %>% 
  filter(Sex == "Total") %>% 
  filter(Age == "15 years or over")

phs_once

sort(unique(phs_once$TIME_PERIOD))

 [1] 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024

barplot(table(phs_once$TIME_PERIOD), main = "number of observations of year in the data")

As it appears that after 2007, the number of observations are more significant in number, I will limit my data to 2007 and later. But, since it appears the number of observations drops off in 2024, I will limit my data to a range of 2007-2023.

# input code to limit year range in perceived health status dataset here

education_level <- read_csv("../data/educational_attainment_distribution_age_gender.csv")
education_levels_defined <- read_csv("../data/educational_attainment_distribution.csv")
education_levels_three<- read_csv("../data/educational_attainment.csv")
wellbeing_social<- read_csv("../data/current_wellbeing_exp.csv")

education_level

NA

education_levels_defined

el_third <- education_levels_three %>% 
  filter(Sex == "Total") %>% 
  filter(Age == "From 25 to 64 years") %>% 
  filter(TIME_PERIOD == 2010) %>% 
  filter(OBS_STATUS == "A") %>% 
  filter(REF_AREA == "AUT") %>% 
  filter(STATISTICAL_OPERATION == "OBS")

el_third

NA

el_secondary <- education_levels_defined %>% 
  filter(Sex == "Total") %>% 
  filter(Age == "From 25 to 64 years") %>% 
  filter(TIME_PERIOD == 2010) %>% 
  filter(OBS_STATUS == "A") %>% 
  filter(REF_AREA == "AUT")

el_secondary

NA

# sort(unique(el_once$OBS_VALUE))

# sort(unique(el_once$`Educational attainment level`))

# sort(unique(el_secondary$`Educational attainment level`))

# el_once   %>%  
  # group_by(`Educational attainment level`) %>%
  # summarize(n = n())

# barplot(table(el_once$`Educational attainment level`), main = "number of observations of that education level in the data")

safety_regions <- read_csv("../data/safety_regions.csv")

safety_regions %>% 
  filter(TIME_PERIOD == 2010) %>% 
  filter(REF_AREA == "AUT") #%>% 

  # filter(Sex == "Total") %>% 
  # filter(Age == "15 years or over")  

wellbeing_social %>% 
  filter(TIME_PERIOD == 2022) %>% 
  filter(REF_AREA == "AUT") #%>% 

  # filter(Unit)